We address the problem of policy evaluation in discounted Markov decision processes, and provide instance-dependent guarantees on the $\ell_\infty$-error under a generative model. We establish both asymptotic and non-asymptotic versions of local minimax lower bounds for policy evaluation, thereby providing an instance-dependent baseline by which to compare algorithms. Theory-inspired simulations show that the widely-used temporal difference (TD) algorithm is strictly suboptimal when evaluated in a non-asymptotic setting, even when combined with Polyak-Ruppert iterate averaging. We remedy this issue by introducing and analyzing variance-reduced forms of stochastic approximation, showing that they achieve non-asymptotic, instance-dependent optimality up to logarithmic factors.
We consider reinforcement learning with performance evaluated by a dynamic risk measure. We construct a projected risk-averse dynamic programming equation and study its properties. Then we propose risk-averse counterparts of the methods of temporal differences and we prove their convergence with probability one. We also perform an empirical study on a complex transportation problem.
Temporal difference learning with linear function approximation is a popular method to obtain a low-dimensional approximation of the value function of a policy in a Markov Decision Process. We give a new interpretation of this method in terms of a splitting of the gradient of an appropriately chosen function. As a consequence of this interpretation, convergence proofs for gradient descent can be applied almost verbatim to temporal difference learning. Beyond giving a new, fuller explanation of why temporal difference works, our interpretation also yields improved convergence times. We consider…
To act and plan in complex environments, we posit that agents should have a mental simulator of the world with three characteristics: (a) it should build an abstract state representing the condition of the world; (b) it should form a belief which represents uncertainty on the world; (c) it should go beyond simple step-by-step simulation, and exhibit temporal abstraction. Motivated by the absence of a model satisfying all these requirements, we propose TD-VAE, a generative sequence model that learns representations containing explicit beliefs about states several steps into the future, and that…
Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement learning, its theoretical analysis has proved challenging and few guarantees on its statistical efficiency are available. In this work, we provide a simple and explicit finite time analysis of temporal difference learning with linear function approximation. Except for a few key insights, our analysis mirrors standard techniques for analyzing stochastic gradient d…
Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to nonconvexity and even divergence in optimization. As a result, the global convergence of neural TD remains unclear. In this paper, we prove for the first time that neural TD converges at a sublinear rate to the global optimum of the mean-squared projected Bellman error for policy evaluation. In particular, we show how such global convergence is enabled by the over…
A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, reapplying them at each iteration. We argue that, unlike in supervised learning, momentum in Temporal Difference (TD) learning accumulates gradients that become doubly stale: not only does the gradient of the loss change due to parameter updates, the loss itself changes due to bootstrapping. We first show that this phenomenon exists, and then propose a first-order correction term to momentum. We show that this correction term improves sample efficiency in p…
We consider the off-policy evaluation problem in Markov decision processes with function approximation. We propose a generalization of the recently introduced \emph{emphatic temporal differences} (ETD) algorithm \citep{SuttonMW15}, which encompasses the original ETD($λ$), as well as several other off-policy evaluation algorithms as special cases. We call this framework \ETD, where our introduced parameter $β$ controls the decay rate of an importance-sampling term. We study conditions under which the projected fixed-point equation underlying \ETD\ involves a contraction operator, allowing us to…
Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new policy-evaluation algorithms that fill a longstanding algorithmic void in reinforcement learning: combining robustness to off-policy sampling, function approximation, linear complexity, and temporal difference (TD) updates. This paper contains two main contributions. First, we derive two new hybrid TD policy-evaluation algorithms, which fill a gap in this collec…
Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address a bias-variance trade off between reliance on current estimates, which could be poor, and incorporating longer sampled reward sequences into the updates. Especially in the off-policy setting, where the agent aims to learn about a policy different from the one generating its behaviour, the variance in the updates can cause learning to diverge as the number of…
Q-learning is a reliable but inefficient off-policy temporal-difference method, backing up reward only one step at a time. Replacing traces, using a recency heuristic, are more efficient but less reliable. In this work, we introduce model-free, off-policy temporal difference methods that make better use of experience than Watkins' Q(λ). We introduce both Optimistic Q(λ) and the temporal second difference trace (TSDT). TSDT is particularly powerful in deterministic domains. TSDT uses neither recency nor frequency heuristics, storing (s,a,r,s',δ) so that off-policy updates can be performed after…
Recently, a new multi-step temporal learning algorithm, called $Q(σ)$, unifies $n$-step Tree-Backup (when $σ=0$) and $n$-step Sarsa (when $σ=1$) by introducing a sampling parameter $σ$. However, similar to other multi-step temporal-difference learning algorithms, $Q(σ)$ needs much memory consumption and computation time. Eligibility trace is an important mechanism to transform the off-line updates into efficient on-line ones which consume less memory and computation time. In this paper, we further develop the original $Q(σ)$, combine it with eligibility traces and propose a new algorithm, call…
We derive an equation for temporal difference learning from statistical principles. Specifically, we start with the variational principle and then bootstrap to produce an updating rule for discounted state value estimates. The resulting equation is similar to the standard equation for temporal difference learning with eligibility traces, so called TD(lambda), however it lacks the parameter alpha that specifies the learning rate. In the place of this free parameter there is now an equation for the learning rate that is specific to each state transition. We experimentally test this new learning …
Because reinforcement learning suffers from a lack of scalability, online value (and Q-) function approximation has received increasing interest this last decade. This contribution introduces a novel approximation scheme, namely the Kalman Temporal Differences (KTD) framework, that exhibits the following features: sample-efficiency, non-linear approximation, non-stationarity handling and uncertainty management. A first KTD-based algorithm is provided for deterministic Markov Decision Processes (MDP) which produces biased estimates in the case of stochastic transitions. Than the eXtended KTD fr…
We consider emphatic temporal-difference learning algorithms for policy evaluation in discounted Markov decision processes with finite spaces. Such algorithms were recently proposed by Sutton, Mahmood, and White (2015) as an improved solution to the problem of divergence of off-policy temporal-difference learning with linear function approximation. We present in this paper the first convergence proofs for two emphatic algorithms, ETD($λ$) and ELSTD($λ$). We prove, under general off-policy conditions, the convergence in $L^1$ for ELSTD($λ$) iterates, and the almost sure convergence of the appro…
Reinforcement learning lies at the intersection of several challenges. Many applications of interest involve extremely large state spaces, requiring function approximation to enable tractable computation. In addition, the learner has only a single stream of experience with which to evaluate a large number of possible courses of action, necessitating algorithms which can learn off-policy. However, the combination of off-policy learning with function approximation leads to divergence of temporal difference methods. Recent work into gradient-based temporal difference methods has promised a path t…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
In this paper, we consider the policy evaluation problem in multi-agent reinforcement learning (MARL) and derive exact closed-form formulas for the finite-time mean-squared estimation errors of decentralized temporal difference (TD) learning with linear function approximation. Our analysis hinges upon the fact that the decentralized TD learning method can be viewed as a Markov jump linear system (MJLS). Then standard MJLS theory can be applied to quantify the mean and covariance matrix of the estimation error of the decentralized TD method at every time step. Various implications of our exact …
Using insight from numerical approximation of ODEs and the problem formulation and solution methodology of TD learning through a Galerkin relaxation, I propose a new class of TD learning algorithms. After applying the improved numerical methods, the parameter being approximated has a guaranteed order of magnitude reduction in the Taylor Series error of the solution to the ODE for the parameter $θ(t)$ that is used in constructing the linearly parameterized value function. Predictor-Corrector Temporal Difference (PCTD) is what I call the translated discrete time Reinforcement Learning(RL) algori…
Understanding the affective, cognitive and behavioural processes involved in risk taking is essential for treatment and for setting environmental conditions to limit damage. Using Temporal Difference Reinforcement Learning (TDRL) we computationally investigated the effect of optimism in risk perception in a variety of goal-oriented tasks. Optimism in risk perception was studied by varying the calculation of the Temporal Difference error, i.e., delta, in three ways: realistic (stochastically correct), optimistic (assuming action control), and overly optimistic (assuming outcome control). We sho…
Korea Institute of Science and Technology Information（韩国科学技术信息研究院）；University of Lyon 2（里昂第二大学）
Evolutionary clustering aims at capturing the temporal evolution of clusters. This issue is particularly important in the context of social media data that are naturally temporally driven. In this paper, we propose a new probabilistic model-based evolutionary clustering technique. The Temporal Multinomial Mixture (TMM) is an extension of classical mixture model that optimizes feature co-occurrences in the trade-off with temporal smoothness. Our model is evaluated for two recent case studies on opinion aggregation over time. We compare four different probabilistic clustering models and we show …
Here, we provide a supplementary material for Takayuki Osogami, "Uncorrected least-squares temporal difference with lambda-return," which appears in {\it Proceedings of the 34th AAAI Conference on Artificial Intelligence} (AAAI-20).
Although deep networks have been widely adopted, one of their shortcomings has been their blackbox nature. One particularly difficult problem in machine learning is multivariate time series (MVTS) classification. MVTS data arise in many applications and are becoming ever more pervasive due to explosive growth of sensors and IoT devices. Here, we propose a novel network (IETNet) that identifies the important channels in the classification decision for each instance of inference. This feature also enables identification and removal of non-predictive variables which would otherwise lead to overfi…
Temporal-difference (TD) networks are a class of predictive state representations that use well-established TD methods to learn models of partially observable dynamical systems. Previous research with TD networks has dealt only with dynamical systems with finite sets of observations and actions. We present an algorithm for learning TD network representations of dynamical systems with continuous observations and actions. Our results show that the algorithm is capable of learning accurate and robust models of several noisy continuous dynamical systems. The algorithm presented here is the first f…
This paper presents four different ways of looking at the well-known Least Squares Temporal Differences (LSTD) algorithm for computing the value function of a Markov Reward Process, each of them leading to different insights: the operator-theory approach via the Galerkin method, the statistical approach via instrumental variables, the linear dynamical system view as well as the limit of the TD iteration. We also give a geometric view of the algorithm as an oblique projection. Furthermore, there is an extensive comparison of the optimization problem solved by LSTD as compared to Bellman Residua…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；ETH Zurich（苏黎世联邦理工学院）；c3.ai Digital Transformation Institute（c3.ai数字化转型研究院）
In this paper, we study the dynamics of temporal difference learning with neural network-based value function approximation over a general state space, namely, \emph{Neural TD learning}. We consider two practically used algorithms, projection-free and max-norm regularized Neural TD learning, and establish the first convergence bounds for these algorithms. An interesting observation from our results is that max-norm regularization can dramatically improve the performance of TD learning algorithms, both in terms of sample complexity and overparameterization. In particular, we prove that max-norm…
Although aviation accidents are rare, safety incidents occur more frequently and require a careful analysis to detect and mitigate risks in a timely manner. Analyzing safety incidents using operational data and producing event-based explanations is invaluable to airline companies as well as to governing organizations such as the Federal Aviation Administration (FAA) in the United States. However, this task is challenging because of the complexity involved in mining multi-dimensional heterogeneous time series data, the lack of time-step-wise annotation of events in a flight, and the lack of sca…
We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise components in addition to martingale difference noise. We analyze the asymptotic behavior of our framework by relating it to limiting differential inclusions in both time-scales that are defined in terms of the ergodic occupation measures associated with the controlled Markov processes. Finally, we present a solution to the off-policy convergence problem for…
